Table of Contents:
00:08 - Memory Access Optimization
00:12 - Layers of Optimization
00:30 - Why memory access optimization is important
00:56 - Page walks at TLB miss
01:07 - Locality of Data Access
01:22 - Spatial locality
01:50 - Temporal locality
02:04 - Memory Access and Cache Utilization
02:09 - Loop Tiling
03:01 - Processing arrays with two nested loops
04:03 - Tiled implementation
05:25 - Cache blocking
05:37 - How to cache block: tile and permute
05:49 - Strip-mine
05:56 - Permutation
06:13 - Optimization parameter: tile size
06:48 - More details in our book
06:57 - xeonphi.com/book